streaming 接入kafka数据

streaming 接入kafka数据

maven依赖

<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>2.4.0-cdh6.3.0</version>
</dependency>

<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_2.11</artifactId>
<version>2.4.0-cdh6.3.0</version>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>3.0.0-cdh6.3.0</version>
</dependency>

<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>3.0.0-cdh6.3.0</version>
</dependency>

<dependency>
<groupId>log4j</groupId>
<artifactId>log4j</artifactId>
<version>1.2.17</version>
</dependency>

代码示例

import org.apache.log4j.{Level, Logger}
import org.apache.kafka.common.serialization.{IntegerDeserializer, StringDeserializer}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext, kafka010}
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent

object SparkStreamingKafka {
def main(args: Array[String]): Unit = {
//进行kerberos 认证
val JASS="D:\\sparkstreaming\\sparkstreaming_Test\\src\\main\\scala\\kerberos\\jaas.conf"
val KRB5="D:\\sparkstreaming\\sparkstreaming_Test\\src\\main\\scala\\kerberos\\krb5.conf"
System.setProperty("java.security.krb5.conf",KRB5)
System.setProperty("java.security.auth.login.config",JASS)

Logger.getLogger("org.apache.spark").setLevel(Level.OFF)
Logger.getLogger("org.eclipse.jetty.Server").setLevel(Level.OFF)
Logger.getLogger("org,apache.kafka.clients.consumer").setLevel(Level.OFF)

val conf = new SparkConf().setMaster("local[*]").setAppName("WordCount")

//消费者配置
val kafkaParams = Map[String, Object](
"bootstrap.servers" -> "kafka05:30005", //kafka集群地址
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[IntegerDeserializer],
"group.id" -> "test", //消费者组名
"auto.offset.reset" -> "earliest", //earliest 表示存在偏移量的时候从偏移量处开始消费
"security.protocol" -> "SASL_PLAINTEXT",
"enable.auto.commit" -> (false: java.lang.Boolean),//如果是true，则这个消费者的偏移量会在后台自动提交
"sasl.kerberos.service.name" -> "kafka"
);

val topics = Array("zhctesttopic") //消费主题，可以同时消费多个
//创建DStream，返回接收到的输入数据

val ssc = new StreamingContext(conf, Seconds(1)) //刷新时间设置为1秒
ssc.sparkContext.setLogLevel("WARN")

val stream = KafkaUtils.createDirectStream[String, String](
ssc,
PreferConsistent,
Subscribe[String, String](topics, kafkaParams))
//打印获取到的数据，因为1秒刷新一次，所以数据长度大于0时才打印
stream.map(_.key()).foreachRDD(rdd=>rdd.foreach(println))
ssc.start();
ssc.awaitTermination();
}
}